Register and share your invite link to earn from video plays and referrals.

Philip Kiely
@philipkiely
Author of Inference Engineering | Building @baseten | Not an LLM (yet)
Joined December 2018
988 Following    16.6K Followers
Scaling past a trillion parameters requires inference engineers to solve 3 issues: - Width: Routing between hundreds of sparse experts - Depth: Mixing global and local linear attention - Length: Processing 1M-token sequences I asked Ali and Bryce to draw it up. They delivered.
Show more
0
41
2.1K
211
Forward to community